Databricks-GenAI-Assoc Application Development Practice Question
A GenAI engineer is building an agent with LangChain on Databricks. The agent must call a Unity Catalog function `catalog.schema.get_weather` to fetch current weather. They want the LLM to decide when to invoke this function. Which LangChain component should they use to expose the Unity Catalog function to the LLM?
⚠ Common exam trap
Watch out — candidates often confuse data retrieval components like Vector Search with tool-calling mechanisms, overlooking that Unity Catalog functions require a specific toolkit to be exposed as tools.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Databricks Unity Catalog function as a LangChain tool
To let an LLM decide when to call a Unity Catalog function, the function must be presented as a LangChain tool. The `UCFunctionToolkit` from Databricks integrates with LangChain, automatically generating tool definitions from Unity Catalog functions. This enables the agent to invoke the function dynamically based on the conversation, which is essential for building responsive GenAI applications.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Databricks Vector Search retriever
Why it's wrong here
Vector Search retriever is used for semantic search over embedded documents, not for calling arbitrary functions. While it can retrieve relevant information, it cannot execute a function like `get_weather` that returns dynamic data. Using it here would not provide the current weather and would not allow the LLM to trigger the function call.
- ✓
Databricks Unity Catalog function as a LangChain tool
Why this is correct
LangChain provides a `UCFunctionToolkit` that wraps Unity Catalog functions as LangChain tools. This allows the LLM to see the function's metadata and invoke it when needed. The toolkit handles authentication and execution via the Databricks SDK, making it the correct choice for integrating Unity Catalog functions into an agent.
- ✗
MLflow pyfunc model wrapper
Why it's wrong here
An MLflow pyfunc wrapper is used to package models for deployment, not to expose functions as tools for an agent. It does not provide the tool-calling interface needed by LangChain agents. While it could wrap the function, it would not integrate with the agent's decision-making process for invoking tools based on user queries.
- ✗
Databricks SQL Connector
Why it's wrong here
The Databricks SQL Connector is a Python library for executing SQL statements on Databricks, not for exposing Unity Catalog functions as callable tools to an LLM. It lacks the interface required by LangChain agents to invoke functions based on LLM output. It would require manual parsing of LLM responses and SQL execution, defeating the purpose of agentic tool calling.
About these practice questions
One of 330 original Databricks-GenAI-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-GenAI-Assoc exam.